Builds / Nvidia GB10 (unified)
DGX Spark: Inkling 2 Mini NVFP4/MXFP8 on vLLM TP1, 47.7 tok/s eval (Tech2wild)
Last updated:
- GPU(s)
- Nvidia GB10 (unified)
- VRAM / unified memory (GB)
- 128
- CPU
- Nvidia GB10 Grace (Arm)
Amazon ยท eBay (used) ยท Newegg - Motherboard
- not stated
- RAM
- 128 GB LPDDR5X unified per Spark (128 GB total)
- PSU
- not stated
- Other
- 1 NVIDIA DGX Spark
- Reported total cost
- not stated
- Power
- not stated
Measured speed (generation tokens/sec)
| Model | Quant | Engine | tok/s | Prompt processing (tok/s) | Details |
|---|---|---|---|---|---|
| Inkling 2 Mini | NVFP4/MXFP8 + DSpark | vLLM TP1, 1 stream | 47.7 | not stated | โก spec-decode (DSpark (num_speculative_tokens 7))context: 262K standard tier: BF16 KV, gpu-memory-utilization 0.80 (68.89 GiB KV, 1,346,671-token pool)๐ 69-scenario tool eval (2Wild-Model-Eval), one request at a time, temperature 0, reasoning_effort none; decode tok/s as published in Tech2wild's README. Short-chat 72.8 tok/s is a peak and not used. Standard tier one-user chats: about 40 to 45 tok/s. Eval quality 88.4/100. |
| Inkling 2 Mini | NVFP4/MXFP8 + DSpark, FP8 KV | vLLM TP1, 1 stream | 47.3 | not stated | โก spec-decode (DSpark (num_speculative_tokens 7))context: 1M max FP8 tier: 74 GiB FP8 (E4M3) KV, 3,308,911-token pool๐ 69-scenario tool eval (2Wild-Model-Eval), one request at a time, temperature 0, reasoning_effort none; max FP8 tier decode tok/s as published in Tech2wild's README. Short-chat 72.8 tok/s is a peak and not used. Eval quality 87.0/100. |
| Inkling 2 Mini | NVFP4/MXFP8 + DSpark, FP8 KV | vLLM TP1, 1 stream | 47.2 | 1,693 @ 199,989-token prompt est. TTFT @8k โ 4.8 s (calculated from measured prefill) measured TTFT: 118 s @ 199,989-token prompt | โก spec-decode (DSpark (num_speculative_tokens 7))context: 199,989-token prompt on the 1M max FP8 tier (74 GiB FP8 KV)๐ Single-request needle test at 50% depth as published in Tech2wild's README; the README says needle-row decode comes from short answers (77 tokens) and is rough. Prefill = prompt tokens / TTFT. Needle PASS. |
| Inkling 2 Mini | NVFP4/MXFP8 + DSpark, BF16 KV | vLLM TP1, 1 stream | 28.3 | 1,680 @ 199,989-token prompt est. TTFT @8k โ 4.9 s (calculated from measured prefill) measured TTFT: 119 s @ 199,989-token prompt | โก spec-decode (DSpark (num_speculative_tokens 7))context: 199,989-token prompt on the 1M max BF16 tier (80 GiB BF16 KV, 2,075,828-token pool)๐ Single-request needle test at 50% depth as published in Tech2wild's README; the README says needle-row decode comes from short answers (149 tokens) and is rough. Prefill = prompt tokens / TTFT. Needle PASS. |
| Inkling 2 Mini | NVFP4/MXFP8 + DSpark, FP8 KV | vLLM TP1, 1 stream | 18.4 | 598 @ 949,953-token prompt est. TTFT @8k โ 13.7 s (calculated from measured prefill) measured TTFT: 1,588 s @ 949,953-token prompt | โก spec-decode (DSpark (num_speculative_tokens 7))context: 949,953-token prompt on the 1M max FP8 tier (74 GiB FP8 KV)๐ Single-request needle test at 50% depth as published in Tech2wild's README; the README says needle-row decode comes from short answers (91 tokens) and is rough. Prefill = prompt tokens / TTFT. Needle PASS (answered correctly at ~950K). |
Prompt processing = prefill speed (how fast the prompt is read) as reported by the source, with the prompt length it was measured at; blank = the source does not report it. est. TTFT @8k is calculated from the measured prefill speed (8,192 รท prefill tok/s), shown only when prefill was measured on a prompt of 512+ tokens. It is not a measurement and ignores load time and caching. measured TTFT is the source's own time-to-first-token. Why prefill matters for coding assistants.
Numbers by Tech2wild (tonyd2wild); Thinking Machines Lab official NVFP4/MXFP8 checkpoint; vLLM inkling-2-mini image and Inkling 2 Mini recipe (recipes.vllm.ai/thinkingmachines/Inkling-2-Mini). RigBase read the GitHub README on 2026-11-21 and checked each figure against the text. RigBase did not re-run it. Speculative decoding (MTP/DFlash/DSpark) inflates predictable text; these rows prefer prose/code over counting peaks. Recipe license: MIT.
https://github.com/tonyd2wild/Inkling-2-Mini-NVFP4-DGX-Spark/blob/main/README.md
https://recipes.vllm.ai/thinkingmachines/Inkling-2-Mini
Blank fields = not stated in the source. We never estimate build data; GPU street prices above are separately sourced and dated.
Quick answers: Can DGX Spark (GB10) run Inkling 2 Mini?
Speculative-decoding rows on this page are not like-for-like with plain decode. See how much MTP and DFlash really speed things up (measured pairs).